Skip to content
Apart Research
Apart Research
Contact us
Sprint projectJun 22, 2026

Garud-AI

1

Submitted to Global South AI Safety Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Garud-AI

Open in a new tab (opens in new tab)
Code (opens in new tab)
Share

Garud AI is a hybrid rule-based + machine learning dashboard that detects scams, fake news, hate speech, financial fraud, and misinformation in text messages. It combines an explainable 5-module rule engine with a Naive Bayes ML classifier (97.5% accuracy), giving users both a transparent reasoning and a statistically confident verdict — fully offline, no API dependency.

Reviews

Judging this Sprint?

Review this project

Your public critique appears on this page without your name. Your private critique is not published; only the Apart team reads it. If you agree below, we share your review with grantmaking.ai (opens in new tab) and the Transformative AI Fund so strong projects can be funded.

Not shown on this page.

Shown on this page, without your name.

Only the Apart team reads this, and funders if you agree below.

Share my name publicly on grantmaking.ai *
Share my private critique with funders *

How much would this matter for AI safety if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical AI safety problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.

  1. As a product this is the most finished one I got. It works offline, it is fast, it explains itself to the user, and you describe the bugs you found and fixed in an honest way. I read the code and it confirms how it works. But the main number is a problem. The 97 percent is only for spam, which is the easiest and oldest task on your list. The other four harms, like hate speech and fake news, are only keyword lists in the code with no testing at all. So one easy number is shown like it describes the whole product. Also a perfect score usually means the test was too easy, not that the tool is perfect. Please either say clearly what is tested and what is not, or test the other parts too. Being honest about this will make people trust the tool more, even if the number goes down.

  2. 1. Naive Bayes doesn't work well in production instances - you can look to improve using other algorithms

    2. LLM architecturally is a better way to solve this

  3. Strengths: Demonstrates a clear application of AI to solve a meaningful problem and communicates the solution effectively. The overall concept shows promise and practical relevance. Areas for Improvement: Expand the technical discussion around model architecture, training methodology, evaluation metrics, and deployment strategy. Including quantitative performance results, robustness testing, and comparisons with baseline approaches would better demonstrate the project's maturity and technical contribution.

Cite this project

@misc{12026garudai,
  title = {{Garud-AI}},
  author = {1},
  year = {2026},
  month = jun,
  note = {Submitted to Global South AI Safety Hackathon, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/garudai-8510}},
  url = {https://apartresearch.com/sprints/projects/garudai-8510}
}

More from Global South AI Safety Hackathon

All 216 entriesBrowse all projects

Build something like this at the next Sprint

AI Collusion Research Sprint · Oct 23 - 25, 2026